earheart AGENTS.md

Contribution instructions for Earheart, a project that uses GitHub Flow, a method where changes are made on short-lived branches and merged through reviewed pull requests. They cover branching, checks, release-triggering pull-request titles, and preserving user transcripts.

In plain words
What is it for?
Use them when making changes to Earheart. They guide branch creation, local validation, pull-request naming, release handling, and preservation of transcript fallbacks.
Why use it?
They reduce the risk of publishing unfinished work, breaking the main branch, or losing source text. They also explain project-specific rules that ordinary Git knowledge may not cover.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/cleanunicorn/earheart/agents-md
Clone the repo
git clone --depth 1 https://github.com/cleanunicorn/earheart

Made for: Codex, OpenCode.

Per session 1,703 This file is loaded in full into every session.
When invoked 1,703 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01703 $0.01703
Opus 5 $0.00851 $0.00851
Sonnet 5 $0.00341 $0.00341
Haiku 4.5 $0.00170 $0.00170

Measured 3d ago against content hash 8d6581698059, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

earheart AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI agents (and humans) contributing to Earheart. This project follows the GitHub flow: main is always releasable, all work happens on short-lived branches, and every change lands through a reviewed pull request.

Read CONTRIBUTING.md for full setup, build, and architecture details. This file is the operational checklist for how to work here.

Golden rules

  1. Never commit directly to main. It is protected and is the release branch — merging to it auto-publishes a release (see below). Always branch.
  2. Never push to main or force-push a shared branch.
  3. The PR title is load-bearing. It drives the released version bump, so it must be a valid Conventional Commits string (see PR titles).
  4. Keep main green. Run the checks locally before opening a PR.
  5. Never lose the user's words. A core design constraint of the app — if you touch the pipeline, preserve the raw-transcript fallbacks.

The GitHub flow, step by step

1. Start from an up-to-date main

git checkout main
git pull origin main

2. Create a branch

Branch names are short, lowercase, hyphenated, and prefixed by intent. Match the Conventional Commits type you expect the PR to use:

feat/<short-description>      # new feature
fix/<short-description>       # bug fix
refactor/<short-description>  # internal change, no behavior change
docs/<short-description>      # documentation only
chore/<short-description>     # tooling, deps, housekeeping

Examples: feat/overlay-copy-button, fix/windows-autostart-readback, docs/agents-guide.

git checkout -b fix/windows-autostart-readback

3. Make focused changes

  • One logical change per PR. Don't bundle an unrelated refactor into a fix.
  • Match the surrounding style: plain JavaScript, no bundler, few runtime deps. Stay close to Electron built-ins and platform tools rather than adding npm packages — the only runtime deps are the two native engines.
  • Keep diffs small and reviewable.

Read the full file on GitHub · 182 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 182 lines · 1,703 tokens per session scan A 8d6581698059

Subscribe to this mod's changes

earheart AGENTS.md is an instructions file published in the GitHub repository cleanunicorn/earheart (22 stars, last pushed 4d ago), licensed MIT. It adds 1,703 tokens to every session, about $0.0085 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.